If you're impatient for the latest versions, I use https://github.com/Guyanonymous-x/guyanonymous_wildcards to manage all of the revisions.

I upload the same file for multiple models, though they're all identical. I upload almost all image examples for each version in the plainly named version - e.g., v112 so if you want to see those - just switch to the v112 version instead of v112 Krea, for example, and you'll be able see much more of what eave version has added.

Here, we're going from v109 to v112. This version adds a huge amount of everyday-world content: 1,422 locations, every object kind in them with era looks, architectural fixtures, trading cards, card and board games, adventure and workout activities and clinical medical scenes. I recommend checking the model changelog (very bottom of this document). In this version, the Showcase prompt files highlight what was added in this version, while the sample prompt files are representative of everything the pack can do.

Because it has grown so much, knowing there are versions with files sorted by folder as well as the one-folder-for-everything model is important - pick the one that works for you. All are included in the zip.

This wildcard project is managed on GitHub, for anyone who wants the most current versions: https://github.com/Guyanonymous-x/guyanonymous_wildcards

Short descriptions

Every kind of adult, from every corner of the world, dressed in anything from a 5,000-year-old tunic to a plush hot-dog costume.

Guyanonymous' Wildcards gives your text-to-image prompts the whole world to draw from: more than 109,400 drop-in .txt files and 4 million lines covering adult characters of every age, body, ancestry and gender identity, plus garments and costumes from the Palaeolithic to today, accessories, footwear, makeup, tattoos, weapons, armour, surfboards and the places they stand in. *It's a big collection. I use https://civarchive.com/models/3016893/guyanonymous-wildcard-prompt-studio for designing my prompts and with this big a pack, it helps!

Most wildcard packs repeat the same faces, clothes and colours. Guyanonymous' Wildcards is built to do the opposite. It is a folder of plain .txt files that you drop into any wildcard-aware image tool and call with a name wrapped in double underscores. Build adult characters aged 18 to 120 with weighted bodies, hair, skin and clothing, or let one prompt pick a person in proportion to the world's adult population, by region or by country. Dress them from garment families that run from ballet to biker, flapper to festival, swimwear to formal wear, corsets to onesies; uniforms and costumes; 37 eras of dress; more than 35 accessory families; a full footwear system; and costumes for fursuiters, cosplayers, LARP and drag. Control sunburn and tan against each person's natural skin tone, dress them for any season or weather, add makeup, nails, piercings and body art, and set the scene in buildings, rooms and landscapes from every region. Everything is for making adult characters only, original wording, and written to embrace global diversity.

What's new since V109

Version 112 (this release)

• Film (film_): film-making styles by genre and by genre per era; Muybridge-style motion studies (muybridge_) of people and animals, past, present and future.

• Holidays: 99 holiday characters from around the world (hol_), holiday clothing with sayings, decorations for 20 occasions (hol_decor_), and Festivus with 29 more novelty holidays (novelty_).

• Lairs (loc_lair_): 100 supervillain lairs and 100 superhero hideouts across every era, cost and size, each with rooms, objects, souvenirs, tech, weapons, traces and conditions.

• Costumes (costume_): 100 themes at six levels from screen-accurate to cheap bagged and flirty; mascot suits (mascot_) and fursuits (fursuit_) of 50 species and five styles.

• Religious figures (relig_): 199 gods, saints, prophets, demigods and sacred beings from 31 traditions, in short, medium and long forms and each tradition's own art styles, plus a symbol-only picture for every figure; figures whose faiths restrict images appear as symbols only.

• Curiosities: 109 cabinets of curiosity (cab_), shrunken heads (shrunken_), hides, furs, animal parts and the crafts made from them, illegal goods plain and seized (animal_), and bad and horror taxidermy (taxi_).

• Also new: sleepwalking (sleepwalk_), ray guns in layers across 14 eras and genres (raygun_), criminal wardrobes and tools for 30 types at every level and style (crim_), 221 lost, legendary, ancestral, fictional and future peoples (peoples_), zoos and menageries from cruel to excellent (zoo_), pop-up books (popup_), blueprints, diagrams and patent drawings (blueprint_), and special events (event_): weddings, funerals, adult birthday parties and anniversary parties, big to small, extravagant to cheap, classy to tacky, flawless to disastrous; performers (perf_): bands, solo singers, karaoke, vaudeville, circus and sideshow acts with their wardrobe, gear, stages, crowds and views; bookstores, newsstands and magazine shops around the world (bookshop_); wear modifiers (wearmod_) that add realistic stains, marks and dents to any garment or object.

• Fixes: mounted animals now say taxidermy, so they render as real specimens instead of plush toys.

Version 111

• Things going wrong (mis_): 20 mishaps for each of 134 activities (sports, music, crafts, hobbies, adventure and workouts) in three levels, small, mid and big, each with its own faces, bystanders and body positions; big ones add the aftermath. People are any adult age, injuries are everyday and non-gory, and eyes are on what is going wrong.

• Bad snapshots: people react to the moment and look at it (away from the lens), with 54 moments, 16 posed-photo mishaps, bystanders, places and outfits, plus framing mistakes (cut-off heads, animals blocking the view, a thumb over the lens) and bird droppings.

• Awkward family photos: many more eras, backdrops, outfit themes, adults, children (always clothed, in lists that reach nothing else), poses, oddities and mishaps that show the reaction.

• Wheels: skateboarding and surfing join the extreme sports; roller skating by era (1870s halls, 1920s clamp-on skates, 1950s rinks, 1970s roller disco, 2020s revival), roller derby, and inline skating (the late-1980s and 1990s boom, aggressive inline, today), each with era outfits, places and mishaps.

• Dance (dance_): 32 styles across solo, pairs and groups, from ballet, tap, flamenco and voguing to the waltz, Argentine tango, salsa and lindy hop, line dancing, ceilidh, disco, K-pop and Bollywood, plus pole fitness, twerking, the haka, the Sufi whirling sema, ancient-style hula, the lion dance and Bon Odori; every step line gives the body position, with holds, formations, outfits, music and places.

• Fad dances (dance_fad_): 25 from the Charleston and the Twist to the Floss, each with its signature move; crowd dancing (dance_crowd_): how people dance to 23 kinds of music by decade, from 1950s jiving and punk pogoing to raves and festival bass drops; and dance-floor mishaps.

• Showcase files: 16 prompts (two from each new area) at 512, 1024 and 1408, plus a zip of 8 new-area showcases of 20 prompts each at 1024; 100 sample prompts representing everything the library can do, at the three sizes (steps 50, cfg 3.75).

Version 110

• Locations: 3,755 weak place lines rewritten and checked inside their prompt sentences (writer's notes removed, fragments made into full descriptions, 'no X' lines turned into what is there, palettes given colours, signs and labels given quoted wording from 84 new loc_text_* lists); 169 regional lines rewritten as short regional versions.

• Heat shimmer: the desert line now fits its scenes, and six new hot things (road, airport tarmac, barbecue, car bonnet, jet exhaust, bonfire) each come in a real and a spectacle version.

• Awkward family photos (afp_): era studio styles, matching outfits, backdrops, poses, odd props and mid-pose mishaps. These lists are self-contained; children appear only here, always clothed, and the build checks that they cannot reach any other file.

• Bad snapshots (snap_): adults caught at the worst moment, natural or mid-pose, and a separate adults-only exposure list (snap_exposure_prompt).

• Objects: bad taxidermy (ob_taxidermy_), mounted heads on walls (ob_mounted_head_, humans only as joke props) and trophies of every kind (ob_trophy_), with photo prompts; all in the object roll-ups.

• Breakdancing joins the extreme sports (adv_breakdance_) with moves, crews, places and action cameras.

• Infrared and UV photo styles (irstyle_): 8 filters, each through its processing (straight from camera, red/blue swapped, black and white, unbalanced), with what glows and what goes dark.

• Ways of seeing people (seeing_): auras, X-rays, heat maps, night vision, lidar and more; glasses prescriptions (acc_glasses_rx) from eyes shrunk by strong minus lenses to owlish strong plus, bifocals and varifocals.

• Zombies, vampires, werewolves, the fae and fairies (myth_): 12 looks each across genres and cultures, in 9 treatments (ultra-realistic to children's animation style) and 17 eras.

• Maps (map_): 38 map types, 13 projections, 12 styles from ancient to treasure maps, with mediums, conditions, details, titles and views.

• Rule check: fewer false reports (sign-up and sign-out, label printers, 'a Uruguayan'); landscape prompts read 'A landscape of desert dunes'.

• Showcase files (34 prompts, two from each new area) and 100 sample prompts at 512, 1024 and 1408 pixel counts (steps 50, cfg 3.75), plus a zip of 17 new-area showcases of 20 prompts each at 1024.

Showcase and sample files: the showcase files highlight what is new or changed in this version, while the sample files are representative of everything the model can do.

Features at a glance

• Whole-world characters. Adults aged 18 to 120 in nine age brackets, with weighted body types, hair, eyes, skin and clothing. One prompt can pick a person by real world population shares, by region or by country. Ethnicity lines now always state a skin colour that fits the group.

• Women's and men's sets. Matching female (f_) and male (m_) files, plus shared files, and demographic layers for cisgender, trans, non-binary, androgynous, intersex and individualized-transition identities, described by who people are.

• Garments. Families by type, era and subculture (about 560 files) with optional _detail versions that describe front, back, coverage and cut so the name is not doing all the work. Includes swimwear, lingerie, sleepwear, corsets, onesies, modest and revealing lines, and rave, festival and counterculture clothing.

• Uniforms and costumes. Hundreds of uniforms, ceremonial dress and cosplay archetypes, Halloween masks and costumes, and character costume for fursuit, cosplay, LARP, faire, reenactment, sci-fi, fantasy and drag.

• Accessories and footwear. More than 50 accessory families in six grades from basic to showpiece, about 430 shoe types, and assistive and adaptive items. Footwear now has quality files that run from cheap to absurdly expensive, with no prices. A wardrobe_ index sorts items into worn dress, adornment and carried items.

• Body and skin. Makeup, nails, piercings, body art, tattoos and skin features, a clinical wound and injury overlay (body_wound_*, by severity and by category: puncture, fracture, burn, contagion, bite and sting, and more) with matching casts, splints and bandages (acc_medwrap_*), plus skin_tan_* files that apply a tan (faint to deepest) or sunburn (pink to blistered to peeling) in a way that is realistic for the person's natural skin tone.

• Condition. condition_* files describe any item's state, from pristine and brand new to old, worn, stained, marked and ruined, so they can be applied to anything in the library.

• Weather and seasons. 20 weather conditions with matching outfits, from heatwave to blizzard.

• Period dress. 37 eras from the Palaeolithic to the 2010s, mixing every region of the world.

• Objects, places and poses. Weapons of the world, armour, surfboards, 13 object families, buildings, rooms, landscapes, and solo and shared poses.

• Art, logos and style packs. Hundreds of original styles for images on objects, fictional logos and tattoos, plus illustration and photographic style packs.

• Locations. 1,422 detailed places in 20 groups, from homes, workplaces and shops to hospitals, transport, outdoor places and odd corners, with scenes, people, times of day, eras and regional versions.

• Everyday objects. Every object kind named in the locations has its own wildcards (forms, materials, wear, details and quoted text where text belongs), with era looks for 230 objects across six periods and 79 architectural fixtures.

• Cards and games. Trading cards in seven decade styles with packs, boxes, displays and five grades of condition; 20 kinds of card game and 36 board and tabletop games with boxes, parts, stages and top-down views. Every word on a card or box is quoted.

• Activities and medicine. 71 adventure, extreme, solo outdoor and workout activities, and clinical medical examinations, treatments and surgery across seven decades.

• Two editions. The full weighted set, and an All Options Once edition with every option listed a single time.

• A library map. docs/Library_Map.html shows how the file names fit together and what each group adds.

• Adults only, original wording. No brands, no real people, no prices, and no minors in any prompt.

Naming guide

Version 36 unified the file names. A name now reads family, group, variant:

• f_ / m_: female and male person files. Files with no prefix are shared.

• age##_##_: one layer per age bracket. bt_: body-type layers.

• clothing_garment_, clothing_uniform_, clothing_onesie_, clothing_period_: all clothing, under one prefix.

• acc_<family>_: accessories, with footwear as acc_shoe_. Tiers are basic, standard, fine, luxury, showpiece and practical.

• costume_: Halloween and character costume. obj_: objects, weapons, armour and surfboards.

• body_, skin_tan_, tattoo_: makeup, nails, piercings, tan and body art.

• scene_, pose_, wx_: places, poses and weather outfits. world_ and countries_: people by region and country.

• aoo_ in front of any name: the All Options Once edition.

If you used earlier versions, filename_changes.txt lists every old name and its new name. Some entry points changed: __garment_prompt__ is now __clothing_garment_prompt__, and __period_prompt__ is now __clothing_period_prompt__.

Getting started

1. Unzip and copy. Unzip Guyanonymous_Wildcards_v112.zip and copy the wildcards folder into your image tool's wildcard folder. Python is not needed to use it.

2. Call a file. Put the file name between double underscores in a prompt, for example __f_prompt_master_by_age__ for a woman or __m_prompt_master_by_age__ for a man.

3. Try a layer. Use __world_person__ for a random person in world proportions, __acc_prompt__ for an accessory, __clothing_garment_prompt__ for a garment, __clothing_period_prompt__ for period dress, __wx_outfit_prompt__ for a weather outfit, or __skin_tan_level__ for a tan or sunburn.

4. Mix and match. Combine them in one prompt, for example a person, then a garment, then an accessory. A blank line in any file means "none". __v38_entry_points__ lists a starting file for each new section.

Optional: run python3 tools/expand.py f_prompt_master_by_age to preview sample prompts, and python3 tools/build_all.py to rebuild everything (about 10 to 15 minutes). The All Options Once edition uses the same names with an aoo_ prefix.

Warning: files that point to other files

Many prompt files in this package are templates. Their lines contain references to other wildcard files, and those files can contain further references. A prompt can therefore be several layers deep, for example __world_person__ calls a region file, which calls a country file, which calls the age, body and clothing files.

This can cause problems. If your image tool does not resolve nested wildcards fully, or stops at a fixed depth, some references may be left in the final prompt as raw text such as __f_age25_34_prompt_char_face__ instead of being replaced. Check a few generated prompts before a big batch, and make sure your tool's wildcard depth or recursion setting is on.

To manage complex, layered prompts, the creator of this package uses Offline Wildcard Prompt Studio, which works with any prompting system. It is a handy way to build and check nested prompts before you run them. The package also includes python3 tools/expand.py to preview prompts and python3 tools/expand.py --check to confirm every reference points to a real file.

Social posts and release note

Short post. Guyanonymous' Wildcards v112 is out: more than 82,000 wildcard files for text-to-image, built for global diversity. New: 1,422 locations with their objects, era-accurate objects and fixtures, trading cards, card and board games, adventure and workout activities and clinical medical scenes. Adults only. Drop it in and go.

Feature post. One prompt, the whole world. __world_person__ picks an adult by region and country in proportion to who actually lives there. Then dress them: kilts, kaftans, kimonos, hanbok, kente, flapper dresses, rave gear, corsets and plush novelty onesies. Add a sunburn, a tan, makeup, piercings, a hearing aid or a wheelchair, and stand them in a Cappadocian cave, a Bauhaus block or a slot canyon in a blizzard. Guyanonymous' Wildcards v112.

Getting-started post. Three steps: unzip, copy the wildcards folder into your image tool, then type __world_person__ in a prompt. That's it. No Python needed. Moving from an older version? filename_changes.txt maps every old name to its new one.

Release note.

Version 112 converts the 350 Locations inventory into 1,422 places with scenes, people, eras and regions; gives every object kind its own wildcards, with era looks for 230 objects and 79 architectural fixtures; and adds trading cards, card games, board games, adventure and workout activities and clinical medical scenes. Every word on cards, boxes and sportswear is quoted.

Changelog (last three versions)

Version 112 (this release)

• Film (film_): film-making styles by genre and by genre per era; Muybridge-style motion studies (muybridge_) of people and animals, past, present and future.

• Holidays: 99 holiday characters from around the world (hol_), holiday clothing with sayings, decorations for 20 occasions (hol_decor_), and Festivus with 29 more novelty holidays (novelty_).

• Lairs (loc_lair_): 100 supervillain lairs and 100 superhero hideouts across every era, cost and size, each with rooms, objects, souvenirs, tech, weapons, traces and conditions.

• Costumes (costume_): 100 themes at six levels from screen-accurate to cheap bagged and flirty; mascot suits (mascot_) and fursuits (fursuit_) of 50 species and five styles.

• Religious figures (relig_): 199 gods, saints, prophets, demigods and sacred beings from 31 traditions, in short, medium and long forms and each tradition's own art styles, plus a symbol-only picture for every figure; figures whose faiths restrict images appear as symbols only.

• Curiosities: 109 cabinets of curiosity (cab_), shrunken heads (shrunken_), hides, furs, animal parts and the crafts made from them, illegal goods plain and seized (animal_), and bad and horror taxidermy (taxi_).

• Also new: sleepwalking (sleepwalk_), ray guns in layers across 14 eras and genres (raygun_), criminal wardrobes and tools for 30 types at every level and style (crim_), 221 lost, legendary, ancestral, fictional and future peoples (peoples_), zoos and menageries from cruel to excellent (zoo_), pop-up books (popup_), blueprints, diagrams and patent drawings (blueprint_), and special events (event_): weddings, funerals, adult birthday parties and anniversary parties, big to small, extravagant to cheap, classy to tacky, flawless to disastrous; performers (perf_): bands, solo singers, karaoke, vaudeville, circus and sideshow acts with their wardrobe, gear, stages, crowds and views; bookstores, newsstands and magazine shops around the world (bookshop_); wear modifiers (wearmod_) that add realistic stains, marks and dents to any garment or object.

• Fixes: mounted animals now say taxidermy, so they render as real specimens instead of plush toys.

Version 111

• Things going wrong (mis_): 20 mishaps for each of 134 activities (sports, music, crafts, hobbies, adventure and workouts) in three levels, small, mid and big, each with its own faces, bystanders and body positions; big ones add the aftermath. People are any adult age, injuries are everyday and non-gory, and eyes are on what is going wrong.

• Bad snapshots: people react to the moment and look at it (away from the lens), with 54 moments, 16 posed-photo mishaps, bystanders, places and outfits, plus framing mistakes (cut-off heads, animals blocking the view, a thumb over the lens) and bird droppings.

• Awkward family photos: many more eras, backdrops, outfit themes, adults, children (always clothed, in lists that reach nothing else), poses, oddities and mishaps that show the reaction.

• Wheels: skateboarding and surfing join the extreme sports; roller skating by era (1870s halls, 1920s clamp-on skates, 1950s rinks, 1970s roller disco, 2020s revival), roller derby, and inline skating (the late-1980s and 1990s boom, aggressive inline, today), each with era outfits, places and mishaps.

• Dance (dance_): 32 styles across solo, pairs and groups, from ballet, tap, flamenco and voguing to the waltz, Argentine tango, salsa and lindy hop, line dancing, ceilidh, disco, K-pop and Bollywood, plus pole fitness, twerking, the haka, the Sufi whirling sema, ancient-style hula, the lion dance and Bon Odori; every step line gives the body position, with holds, formations, outfits, music and places.

• Fad dances (dance_fad_): 25 from the Charleston and the Twist to the Floss, each with its signature move; crowd dancing (dance_crowd_): how people dance to 23 kinds of music by decade, from 1950s jiving and punk pogoing to raves and festival bass drops; and dance-floor mishaps.

• Showcase files: 16 prompts (two from each new area) at 512, 1024 and 1408, plus a zip of 8 new-area showcases of 20 prompts each at 1024; 100 sample prompts representing everything the library can do, at the three sizes (steps 50, cfg 3.75).

Version 110

• Locations: 3,755 weak place lines rewritten and checked inside their prompt sentences (writer's notes removed, fragments made into full descriptions, 'no X' lines turned into what is there, palettes given colours, signs and labels given quoted wording from 84 new loc_text_* lists); 169 regional lines rewritten as short regional versions.

• Heat shimmer: the desert line now fits its scenes, and six new hot things (road, airport tarmac, barbecue, car bonnet, jet exhaust, bonfire) each come in a real and a spectacle version.

• Awkward family photos (afp_): era studio styles, matching outfits, backdrops, poses, odd props and mid-pose mishaps. These lists are self-contained; children appear only here, always clothed, and the build checks that they cannot reach any other file.

• Bad snapshots (snap_): adults caught at the worst moment, natural or mid-pose, and a separate adults-only exposure list (snap_exposure_prompt).

• Objects: bad taxidermy (ob_taxidermy_), mounted heads on walls (ob_mounted_head_, humans only as joke props) and trophies of every kind (ob_trophy_), with photo prompts; all in the object roll-ups.

• Breakdancing joins the extreme sports (adv_breakdance_) with moves, crews, places and action cameras.

• Infrared and UV photo styles (irstyle_): 8 filters, each through its processing (straight from camera, red/blue swapped, black and white, unbalanced), with what glows and what goes dark.

• Ways of seeing people (seeing_): auras, X-rays, heat maps, night vision, lidar and more; glasses prescriptions (acc_glasses_rx) from eyes shrunk by strong minus lenses to owlish strong plus, bifocals and varifocals.

• Zombies, vampires, werewolves, the fae and fairies (myth_): 12 looks each across genres and cultures, in 9 treatments (ultra-realistic to children's animation style) and 17 eras.

• Maps (map_): 38 map types, 13 projections, 12 styles from ancient to treasure maps, with mediums, conditions, details, titles and views.

• Rule check: fewer false reports (sign-up and sign-out, label printers, 'a Uruguayan'); landscape prompts read 'A landscape of desert dunes'.

• Showcase files (34 prompts, two from each new area) and 100 sample prompts at 512, 1024 and 1408 pixel counts (steps 50, cfg 3.75), plus a zip of 17 new-area showcases of 20 prompts each at 1024.

The full history of every version is in CHANGELOG.txt inside the zip. Since version 36 the files follow one naming structure; see the naming guide above, and filename_changes.txt for every old and new name.